Enhancing Bias Assessment for Complex Term Groups in Language Embedding Models: Quantitative Comparison of Methods.

Journal: JMIR medical informatics
Published Date: Nov 12, 2024

Abstract

BACKGROUND: Artificial intelligence (AI) is rapidly being adopted to build products and aid in the decision-making process across industries. However, AI systems have been shown to exhibit and even amplify biases, causing a growing concern among people worldwide. Thus, investigating methods of measuring and mitigating bias within these AI-powered tools is necessary.

Authors

  • Magnus Gray
    Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, 3900 NCTR Road, Jefferson, Arkansas 72079 United States.
  • Mariofanna Milanova
    Department of Computer Science, Donaghey College of Science, Technology, Engineering, and Mathematics, University of Arkansas at Little Rock, Little Rock, AR, United States.
  • Leihong Wu
    Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, U.S. Food and Drug Administration, 3900 NCTR Rd, Jefferson, AR, 72079, USA. Leihong.wu@fda.hhs.gov.

Keywords

External Resources

Popular Topics
Recent Journals